Wan Musa
My Resume

My AI Work

Systems I've designed and built.

Each project starts from a real workflow. This collection grows as new systems are deployed.

Agentic workflowDeployed — personal system

Telegram - Gmail Assistant

An event-driven Gmail assistant that classifies incoming messages and brings decisions into Telegram, with human approval before sending replies or creating calendar events.

View on GitHub
  • Python
  • FastAPI
  • Google Pub/Sub
  • LangGraph
Read case study
InfrastructureDeployed — personal platform

Shared AI Infrastructure

A reusable Docker Compose foundation for hosting multiple AI applications on a single Oracle VPS.

View on GitHub
  • Docker Compose
  • External Docker network: ai_platform
  • PostgreSQL 17 (persistent volume)
  • nginxproxy/nginx-proxy
Read case study
Self-hosted LLMDeployed - personal VPS

VPS-Hosted Gemma 3

A shared Gemma 3 inference service on my VPS, exposing authenticated APIs for structured job extraction and lightweight assistant tasks.

View on GitHub
  • Python
  • FastAPI
  • Gemma 3 4B
  • Ollama
Read case study
Browser extensionImplemented - local Chrome tool

Local Web Scraping

A Chrome extension that captures job adverts from the page you are viewing, keeps them in a local review workspace, and exports structured records without an LLM.

View on GitHub
  • JavaScript
  • Chrome Manifest V3
  • DOM extraction
  • Chrome Storage API
Read case study
Multistage data ingestionImplemented - queued pipeline

Job Ad Ingestion & Resume Builder

A multistage workflow that takes browser-captured job adverts through validated intake, a PostgreSQL queue, evidence-grounded generation, and private Word-document storage.

View on GitHub
  • Python
  • FastAPI
  • PostgreSQL
  • Pydantic
Read case study